Creation of a Deep Learning Model for the Enhancement and Reconstruction of Environmental Images

IntroductionNorthern China is considered a global hotspot of biodiversity loss due to dramatic climate and land use change characterized by rapid urban expansion. However, little is known that the impacts of these two drivers in shaping the future availability of habitat for plants in urban areas of Northern China, especially at a high spatial resolution.MethodsHere, we modelled the habitat suitability of 2,587 plant species from the flora of Northern China and estimated how future climate and urban expansion may affect species-level plant biodiversity across three shared socioeconomic pathway (SSP) scenarios for the year 2050 in main city clusters.ResultsThe results suggested that climate and urban expansion combined could cause a decline of up to 6.5% in plant biodiversity of Northern China, while urban expansion alone may cause 4.7–6.2% and climate change cause 0.0–0.3% by 2050. The contribution of urban expansion was higher in urban areas, while the contribution of climate change was higher in natural areas. Species may lose an average of 8.2–10.0% of their original environmentally suitable area. Our results verified that the process of urban expansion would necessarily result in large-scale biodiversity loss.DiscussionThe plant biodiversity loss in city clusters of Northern China was mainly determined by urban expansion rather than climatic change. The impact of climate change should not be ignored, since climate change will likely cause a higher reduction of area for some species. Based on these findings, we proposed that plant biodiversity loss in Northern China will accelerate in the future unless both urban expansion change and climate change are minimized.

Urban areas generally have higher near‐surface air temperature and lower air humidity than rural areas. Little is known about how heat stress, the combined effect of high air temperature and high humidity on human physiology, will be affected by future urban land expansion. Here we use a mesoscale numerical weather prediction model to examine the effects of urban land expansion from 2000 to 2050 on heat stress (measured as wet‐bulb globe temperature, WBGT) in the urban areas of China, India, and Nigeria, which are projected to account for one‐third of global urban population growth through 2050. Our results show that urban expansion slightly reduces heat stress during the day (∼0.2°C) but substantially intensifies it at night, by ∼1°C on average and by up to 2–3°C in five mega‐urban regions (MURs). These effects exist with or without climate change induced by rising concentrations of greenhouse gases (GHGs). Installing cool roofs—an urban heat island mitigation measures—can reduce the daytime WBGT by 0.5–1°C, partially offsetting the heat stress conditions caused by GHG‐induced climate change. However, even with cool roofs, the nighttime WBGTs are higher by 0.3–0.9°C over the whole countries studied, and by 1–2°C in the MURs under the urban expansion scenario, compared to the situation in which urban areas remain unchanged. These results show that future urban expansion and heat island mitigation can result in potential daytime benefits but also persistent nighttime risks.

Urbanization is causing profound changes in ecosystem functions at local and regional scales. The net primary productivity (NPP) is an important indicator of global change, rapid urbanization and climate change will have a significant impact on NPP, and urban expansion and climate change in different regions have different impacts on NPP, especially in densely populated areas. However, to date, efforts to quantify urban expansion and climate change have been limited, and the impact of long-term continuous changes in NPP has not been well understood. Based on land use data, night light data, NPP data, climate data, and a series of social and economic data, we performed a comprehensive analysis of land use change in terms of type and intensity and explored the pattern of urban expansion and its relationship with NPP and climate change for the period of 2000–2015, taking Zhengzhou, China, as an example. The results show that the major form of land use change was cropland to built-up land during the 2000–2015 period, with a total area of 367.51 km2 converted. The NPP exhibited a generally increasing trend in the study area except for built-up land and water area. The average correlation coefficients between temperature and NPP and precipitation and NPP were 0.267 and 0.020, respectively, indicating that an increase in temperature and precipitation can promote NPP despite significant spatial differences. During the examined period, most expansion areas exhibited an increasing NPP trend, indicating that the influence of urban expansion on NPP is mainly characterized by an evident influence of the expansion area. The study can provide a reference for Zhengzhou and even the world's practical research to improve land use efficiency, increase agricultural productivity and natural carbon sinks, and maintain low-carbon development.

More than one-third of the land worldwide is located in areas with arid and semiarid climates. Desertification has been increased in these areas during the recent decades. About 80% of that of Iran is located in the arid and semiarid areas. Sand dunes, as an indicator of desert land, cover an area of about 32 million hectares, out of which 12 million hectares have not been stabilized yet. Advancing sand dunes have resulted in much more damage to the agricultural products and urban areas of the region. In this survey, satellite images and aerial photos were employed to evaluate the role of land use changes on desertification within the years 1955, 1997 and 2002. Therefore, IRS (International Revenue Service) images of 2002 and available aerials photos of 1955 and 1997 were used. After making the aerial photos mosaic, processing was dose using ILWIS software. The needed data were completed by field surveying and the land use map was produce for two decades. To produce the land use map using digital processing methods, 10 sample sets (training points) were selected uniformly in the area. After preprocessing including geometric correction, image enhancement and band composition, image classification was done by maximum likelihood method and the land use map was produced. In this phase, the obtained land use map corresponded to the ground truth map, which was achieved using field surveying and recording of the coordinates of the points with GPS pixel to pixel, and accuracy obtained from the numerical classification was estimated to be 0.3%. Then, due to the obtained low accuracy, the visual interpretation method was used to produce the land use map, so the accuracy of 78.5% was achieved. Finally, the area of each land use and the rate of changes were calculated. The results indicated a decrease of 2000 ha in the desert area from 1955 to 1997 and of 160 ha from 1997 to 2002 as well as an increase in the area of the other land uses. The results showed no desertification in the study area, even though land degradation could obviously be identify in the area, resulting from the changes of gardens and agricultural land uses to industrial and urban areas. Key words: Desertification, land use, remote sensing, IRS images, Ardakan, Iran.

Exploring the response of net primary productivity variations to urban expansion and climate change: A scenario analysis for Guangdong Province in China

The characteristics of urban space expansion reflect the changes of urban space layout and space structure, as well as the urban developing direction and urban orientation in the future. Based on the remote sensing image data of 1990, 2000, 2010 and 2020, this paper analyzes the urban space expansion characteristics of Luoyang, by using the urban land compaction index, expansion intensity index and centroid distribution in 4 time sections and 3 periods. The results show that: 1) the urban land area of Luoyang has expanded rapidly, the urban planning policy has successfully guided the urban expansion. 2) In the first period, the urban expansion belongs to the rapid expansion type, mainly filling the built-up area and natural expansion to outward; the second period is of high-speed expansion type, the urban expansion mainly enlarges the urban framework, then fills the expanded district, and the influence of urban natural growth factor is very small; the third period belongs to the high-speed expansion type, and the expansion rate is significantly lower than that in the second period, the urban expansion is mainly to fill in the urban framework enlarged in the previous period and continue to enlarge the urban framework, and the influence of urban natural growth factor is very little. 3) The urban land centroid gradually migrates to the southeast with the azimuth of 151.47°, the annual migration distance is of 138.29 m. The migration rate in the second period is the fastest, which is about 7.43 times that of the first period, and 2.70 times that of the third period. In the first period, the urban land is mainly expanded to southward, with the main azimuth of 201.13°. Compared with the urban land centroid in 2000, the urban land in the second period mainly expands to east-southeast and southward along the azimuths of 141.92° and 154.17° respectively. Compared with the urban centroid in 2010, the urban land in the third period mainly expands in the orientations of southeast and eastward along the azimuth of 96.24° and 133.45°.

Urban expansion has become a widespread trend in developing countries. Road networks are an extremely important factor driving the expansion of urban land and require further study. To investigate the relationship between road networks and urban expansion, we selected Beijing, New York, London, and Chicago as study areas. First, we obtained urban land use vector data through image interpretation using a remote sensing (RS) and geographic information systems (GIS) platform and then used overlay analysis to extract information on urban expansion. A road network density map was generated using the density analysis tool. Finally, we conducted a spatial statistical analysis between road networks and urban expansion and then systematically analyzed their distribution features. In addition, the Urban Expansion-Road Network Density Model was established based on regression analysis. The results indicate that (1) the road network density thresholds of Beijing, New York, London, and Chicago are 18.9 km/km2, 37.8 km/km2, 57.0 km/km2, and 64.7 km/km2, respectively, and urban expansion has an inverted U-curve relationship with road networks when the road network density does not exceed the threshold; (2) the calculated turning points for urban expansion indicate that urban expansion initially accelerates with increasing road network density but then decreases after the turning point is reached; and (3) when the road density exceeds the threshold, urban areas cease to expand. The correlation between urban expansion and road network features provides an important reference for the future development of global cities. Understanding road network density offers some predictive capabilities for urban land expansion, facilitates the avoidance of irregular expansion, and provides new ideas for addressing the inefficient utilization of land.

Climate change will constrain the rapid urban expansion in drylands: A scenario analysis with the zoned Land Use Scenario Dynamics-urban model

Urban land will face high fluvial flood risk against the background of climate change and urban expansion. The effect of urban spatial expansion, instead of densification of assets within existing urban cells, on flood risk has rarely been reported. Here, we project the future flood risk of seven urban agglomerations in China, home to over 750 million people. The inundated urban land areas in the future are projected to be 4 to 19 times that at present. Without considering the urban spatial expansion, the inundated urban land areas will be underestimated by 10-50%. Urban land is more likely to be inundated than non-urban land, and the newly-developed urban land will be inundated more easily than the historical urban land. The results demonstrate the urgency of integrating climate change mitigation, reasonable urban land expansion, and increased flood protection levels to minimize the flood risk in urban land.

Abstract. India's urbanization has resulted in a significant change in many regions for both agricultural land and agricultural land use. However, there is limited understanding about the relationship between the two primary changes occurring to India's agricultural land – the urban expansion on agricultural land and agricultural land use intensity. Our primary goal here is to examine agricultural land change patterns and processes, and their main driving forces in Aligarh region (Uttar Pradesh) during the time periods from 2011 to 2018. We have conducted a remote sensing and GIS based analysis of change pattern using multi-temporal Landsat imageries for the years 2011 and 2018 by investigating the magnitude of changes in agricultural land use intensity across the district in a geographical perspective. Our study captured gradual decrease in the agricultural land in Aligarh district. The results also show that urban expansion is associated with a decline in agricultural land use intensity. The region experienced agriculture transition, and the urban expansion trend persisted till 2018. In terms of the drivers, we believe that the population and economic factors are most influential in shaping urban centers, while lower incentive and climatic shifts are the key drivers of decrease in agricultural land. Our study highlights the drastic effects of socio-economic and climatic changes on links between urbanization, and agricultural land which implies that urban land expansion is highly likely in future and consequently, will create pressure on the country's food security.

Urban expansion and climate change have profoundly affected terrestrial net primary production (NPP), but their relative contributions to NPP changes across varied stages of urban development remain unclear. Furthermore, many studies were conducted at a low resolution (250–1000 m), which may increase the uncertainty of NPP estimates due to mixed pixels. This study used improved multisource data synergized quantitative (MuSyQ) NPP model to estimate NPP in Beijing during 1990–2020 at a 30 meters (m) resolution, and quantified the effects induced by urban expansion and climate change across different urban expansion stages and functional zones. The urban area in Beijing increased by 1823.91 km2 over the study period, the fastest expansion rate occurred between 2000 and 2013, resulting in great NPP loss (18.21 GgCyear−1) (1 Gg = 109 g). The increasingly severe climate change has also led to a reduction in NPP, but this impact is much smaller than the direct loss of NPP caused by urban expansion. Especially between 2000 and 2013, the average annual NPP loss attributed to urban expansion is approximately 22.66 times greater than that caused by climate change. Our findings highlight the urgent need to develop regional strategies to address urban expansion, enhance natural carbon sinks, and achieve sustainable development.

The present study predicts and assesses the individual, combined, and synergistic effect of land-use change and climate change on streamflow, sediment, and total phosphorus (TP) loads under the present and future scenarios by using the Soil and Water Assessment Tool (SWAT). To predict the impacts of climate and land-use change on streamflow, sediment, and TP loads, there are 46 scenarios composed of historical climate, baseline period climate, eight climate models of Coupled Model Intercomparison Project phase 5 (CMIP5) of two representative emission pathways (RCP4.5 and RCP8.5), after downscaled and bias-corrected, two observed land-use maps (LULC 1995, LULC 2015) and the projected two future land-use maps (LU2055 and LU 2075) with the help of CA-Markov model to be fed into SWAT. The central tendency of streamflow, sediment, and TP loads under future scenarios is represented using the annual average. The intra-/inter-annual variation of streamflow, sediment, and TP loads simulated by SWAT is also analyzed using the coefficient of variation. The results show that future land-use change has a negligible impact on annual streamflow, sediment, TP loads, and intra-annual and inter-annual variation. Climate change is likely to amplify the annual streamflow and sediment and reduce the annual TP loads, which is also expected to reduce its inter-/intra-annual variation of TP loads compared with the baseline period (2000–2019). The combined impact of land-use and climate change on streamflow, sediment, and TP loads is greater than the sum of individual impacts for climate change and land-use change, especially for TP loads. Moreover, the synergistic impact caused by the interaction of climate and land use varies with variables and is more significant for TP loads. Thus, it is necessary to consider the combined climate and land-use change scenarios in future climate change studies due to the non-negligible synergistic impact, especially for TP loads. This research rare integrates the individual/combined/synergistic impact of land-use and climate change on streamflow, sediment, and TP loads and will help to understand the interaction between climate and land-use and take effective climate change mitigation policy and land-use management policy to mitigate the non-point source pollution in the future.

Water resources in Mediterranean regions face growing stress due to the combined effects of climate change, land use changes, and anthropogenic pressures. This study investigates the sensitivity of natural and anthropized river flows to these factors, focusing on basins in Tuscany (Italy) and the Valencian Community (Spain). The research uses advanced hydrological models (MOBIDIC and TETIS) to estimate natural and anthropized flows, quantify water stress, and introduce the Ecohydrological Distance Index (EcFI) to assess deviations from ecological sustainability in hydrological regimes.The analysis emphasizes the impact of land use changes and anthropogenic pressures, such as water withdrawals and releases driven by population density and urbanization. Key indices, such as the PREX, which quantifies non-withdrawal pressures (e.g., land use and riparian alterations), and the Water Exploitation Index Plus (WEI+), which measures water stress by comparing abstraction to available resources, highlight critical areas experiencing significant water stress, especially during summer. These indices also provide insights into the drivers of ecohydrological imbalances.A sensitivity analysis explores hydrological systems' responses to climate change (e.g., RCP8.5 scenarios) and human pressures, such as increased water demand from population growth and urban expansion. Results indicate a substantial reduction in summer flows (up to -50%) and a rise in water stress indices (e.g., WEI+) in upstream river segments. Land use changes, particularly urbanization and agricultural expansion, exacerbate water scarcity and ecological degradation, as reflected in the worsening of the EcFI and PREX indices.This study offers a comprehensive framework for assessing the combined impacts of climate change, land use, and human pressures on water resources in Mediterranean basins. Integrating hydrological modeling, ecohydrological indices, and socio-environmental factors provides robust tools for sustainable water management. The findings support policymakers in developing adaptive strategies to mitigate water stress and protect aquatic ecosystems in a changing climate.

<p>The Mediterranean region has been identified as one of the most affected global hot-spots for climate change. Recent climate change in the Mediterranean can be characterized by faster increasing temperatures than the global mean and significant decreases in annual precipitation. Besides, important land cover changes have occurred, such as reforestation, agricultural intensification, urban expansion and the construction of many reservoirs, mainly with the purpose to store water for irrigation. Here we study the impacts of these changes on several ecosystem services in the Segura River catchment, a typical large Mediterranean catchment where many of the before mentioned changes have occurred in the last half century. We applied a hydrological model, coupled with a soil erosion and sediment transport model, to study the impact of climate and land cover change and reservoir construction on ecosystem services for the period 1971-2010. Eight ecosystem services indicators were defined, which include runoff, plant water stress, hillslope erosion, reservoir sediment yield, sediment concentration, reservoir storage, flood discharge and low flow. To assess larger land use changes, we also applied the model for an extended period (1952-2018) to the Taibilla subcatchment, a typical Mediterranean mountainous subcatchment, which plays an important role in the provision of water within the Segura River catchment. As main results we observed that climate change in the evaluated period is characterized by a decrease in precipitation and an increase in temperature. Detected land use change over the past 50 years is typical for many Mediterranean catchments. Natural vegetation in the headwaters increased due to agricultural land abandonment. Agriculture expanded in the central part of the catchment, which most likely is related to the construction of reservoirs in the same area. The downstream part of the catchment is characterized by urban expansion. While land use changed in more than 30% of the catchment, most impact on ecosystem services can be attributed to climate change and reservoir construction. All these changes have had positive and negative impacts on ecosystem services. The positive impacts include a decrease in hillslope erosion, sediment yield, sediment concentration and flood discharge (-21%, -18%, -82% and -41%, respectively). The negative impacts include an increase in plant water stress (+5%) and a decrease in reservoir storage (-5%). The decrease in low flow caused by land use change was counteracted by an increase in low flow due to reservoir construction. The results of our study highlight how relatively small climate and land use changes compared to the changes foreseen for the coming decades, have had an important impact on ecosystem services over the past 50 years.</p>

Determining the impacts of climate change and urban expansion on net primary productivity using the spatio-temporal fusion of remote sensing data